When will the training code be released?

[howardgriffin]

Nice work, but when will the training code be released? I'm hoping for it.

[tgxs002]

Thank you for your interest in our work! Which part of code are you wishing for?

[howardgriffin]

This work is really interesting.
I'm interested in both 'training hpc classifier code' and 'training lora code'. I can't wait for this code being released.

[tgxs002]

HPC training code can be ready soon. I can also upload the LoRA training code, but the training data construction is relatively complex, and may take considerable time for me to add comments / refactor the code / write the doc.

[howardgriffin]

HPC training code can be ready soon. I can also upload the LoRA training code, but the training data construction is relatively complex, and may take considerable time for me to add comments / refactor the code / write the doc.

You can release the training code first if possible. I think this will be very helpful for some people.
As for the training data construction, you can release it later when you are ready.
Thank you for your nice work!

[tgxs002]

Hi Howard, I have just uploaded the LoRA training code. Please note that it hasn't been sanitized, and lacks necessary training environment specifications. I will provide the full training guide when time is available, stay tuned!

[VigneshBaskar]

Hi Blakey
@tgxs002, Any updates on this please? Thank you very much

[tgxs002]

@VigneshBaskar I'm preparing the training script for the classifier. It will be ready in a few days.

[tgxs002]

I have updated the instructions for adapting SD, please check it out! I will also release the training code of the preference classifier in a few days, maybe also with a much stronger preference classifier checkpoint.

[sachinnitw1317]

Thanks, have been waiting for this

[VigneshBaskar]

@VigneshBaskar I'm preparing the training script for the classifier. It will be ready in a few days.

Thank you very much @tgxs002. Please keep us posted. I am super excited for the code

[R2Bb1T]

Is the code of reinforce learning part available now?

[tgxs002]

Here it is: https://github.com/tgxs002/align_sd#training . @R2Bb1T